1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
/*
* utf8.c:
*
* Copyright (c) 2008 James McKenzie <james@fishsoup.dhs.org>,
* All rights reserved.
*
*/
static char rcsid[] = "$Id$";
/*
* $Log$
* Revision 1.4 2008/02/23 13:05:58 staffcvs
* *** empty log message ***
*
* Revision 1.3 2008/02/23 11:48:37 james
* *** empty log message ***
*
* Revision 1.2 2008/02/22 23:39:27 james
* *** empty log message ***
*
* Revision 1.1 2008/02/22 19:12:05 james
* *** empty log message ***
*
*/
#include "project.h"
void
utf8_flush (Context * c)
{
UTF8 *u = c->u;
int i;
switch (u->utf_ptr)
{
case 1:
log_f (c->l, "<invalid utf-8 sequence: \\%03o>", u->utf_buf[0]);
break;
case 2:
log_f (c->l, "<invalid utf-8 sequence: \\%03o \\%03o>",
u->utf_buf[0], u->utf_buf[1]);
break;
case 3:
log_f (c->l, "<invalid utf-8 sequence: \\%03o \\%03o \\%03o>",
u->utf_buf[0], u->utf_buf[1], u->utf_buf[2]);
break;
case 4:
log_f (c->l,
"<invalid utf-8 sequence: \\%03o \\%03o \\%03o \\%03o>",
u->utf_buf[0], u->utf_buf[1], u->utf_buf[2], u->utf_buf[3]);
break;
}
for (i = 0; i < u->utf_ptr; ++i)
vt102_parse_char (c, u->utf_buf[i]);
u->utf_ptr = 0;
u->in_utf8 = 0;
}
void
utf8_parse (Context * c, int ch)
{
UTF8 *u = c->u;
if (ch == SYM_CHAR_RESET)
{
u->in_utf8 = 0;
vt102_parse_char (c, ch);
return;
}
if (!u->in_utf8)
{
/*FIXME: for the moment we bodge utf8 support */
if (ch == 0xb9)
{ /*CSI, not a valid utf8 start char */
vt102_parse_char (c, ch);
}
else if ((ch & 0xe0) == 0xc0)
{ /*Start of two byte unicode sequence */
u->in_utf8 = 1;
u->utf_ptr = 0;
u->utf_buf[u->utf_ptr++] = ch;
u->ch = (ch & 0x1f) << 6;
u->sh = 0;
}
else if ((ch & 0xf0) == 0xe0)
{ /*Start of three byte unicode sequence */
u->in_utf8 = 2;
u->utf_ptr = 0;
u->utf_buf[u->utf_ptr++] = ch;
u->ch = (ch & 0x0f) << 12;
u->sh = 6;
}
else if ((ch & 0xf8) == 0xf0)
{
u->in_utf8 = 3;
u->utf_ptr = 0;
u->utf_buf[u->utf_ptr++] = ch;
u->ch = (ch & 0x07) << 18;
u->sh = 12;
}
else
{
vt102_parse_char (c, ch);
}
}
else
{
if ((ch & 0xc0) != 0x80)
{
utf8_flush (c);
vt102_parse_char (c, ch);
}
else
{
u->utf_buf[u->utf_ptr++] = ch;
u->ch |= (ch & 0x3f) << u->sh;
u->sh -= 6;
u->in_utf8--;
if (!u->in_utf8)
vt102_parse_char (c, ch);
}
}
}
UTF8 *
utf8_new (void)
{
UTF8 *ret;
ret = (UTF8 *) malloc (sizeof (UTF8));
ret->in_utf8 = 0;
}
|
